Joint image compression and denoising via latent-space scalability
When it comes to image compression in digital cameras, denoising is traditionally performed prior to compression. However, there are applications where image noise may be necessary to demonstrate the trustworthiness of the image, such as court evidence and image forensics. This means that noise itse...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-09-01
|
| Series: | Frontiers in Signal Processing |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frsip.2022.932873/full |
| _version_ | 1798026406953746432 |
|---|---|
| author | Saeed Ranjbar Alvar Mateen Ulhaq Hyomin Choi Ivan V. Bajić |
| author_facet | Saeed Ranjbar Alvar Mateen Ulhaq Hyomin Choi Ivan V. Bajić |
| author_sort | Saeed Ranjbar Alvar |
| collection | DOAJ |
| description | When it comes to image compression in digital cameras, denoising is traditionally performed prior to compression. However, there are applications where image noise may be necessary to demonstrate the trustworthiness of the image, such as court evidence and image forensics. This means that noise itself needs to be coded, in addition to the clean image itself. In this paper, we present a learning-based image compression framework where image denoising and compression are performed jointly. The latent space of the image codec is organized in a scalable manner such that the clean image can be decoded from a subset of the latent space (the base layer), while the noisy image is decoded from the full latent space at a higher rate. Using a subset of the latent space for the denoised image allows denoising to be carried out at a lower rate. Besides providing a scalable representation of the noisy input image, performing denoising jointly with compression makes intuitive sense because noise is hard to compress; hence, compressibility is one of the criteria that may help distinguish noise from the signal. The proposed codec is compared against established compression and denoising benchmarks, and the experiments reveal considerable bitrate savings compared to a cascade combination of a state-of-the-art codec and a state-of-the-art denoiser. |
| first_indexed | 2024-04-11T18:34:53Z |
| format | Article |
| id | doaj.art-f5d71dbea81d42909c06bfdb5ae58ead |
| institution | Directory Open Access Journal |
| issn | 2673-8198 |
| language | English |
| last_indexed | 2024-04-11T18:34:53Z |
| publishDate | 2022-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Signal Processing |
| spelling | doaj.art-f5d71dbea81d42909c06bfdb5ae58ead2022-12-22T04:09:19ZengFrontiers Media S.A.Frontiers in Signal Processing2673-81982022-09-01210.3389/frsip.2022.932873932873Joint image compression and denoising via latent-space scalabilitySaeed Ranjbar AlvarMateen UlhaqHyomin ChoiIvan V. BajićWhen it comes to image compression in digital cameras, denoising is traditionally performed prior to compression. However, there are applications where image noise may be necessary to demonstrate the trustworthiness of the image, such as court evidence and image forensics. This means that noise itself needs to be coded, in addition to the clean image itself. In this paper, we present a learning-based image compression framework where image denoising and compression are performed jointly. The latent space of the image codec is organized in a scalable manner such that the clean image can be decoded from a subset of the latent space (the base layer), while the noisy image is decoded from the full latent space at a higher rate. Using a subset of the latent space for the denoised image allows denoising to be carried out at a lower rate. Besides providing a scalable representation of the noisy input image, performing denoising jointly with compression makes intuitive sense because noise is hard to compress; hence, compressibility is one of the criteria that may help distinguish noise from the signal. The proposed codec is compared against established compression and denoising benchmarks, and the experiments reveal considerable bitrate savings compared to a cascade combination of a state-of-the-art codec and a state-of-the-art denoiser.https://www.frontiersin.org/articles/10.3389/frsip.2022.932873/fullimage denoisingimage compressiondeep learningmulti-task compressionscalable coding |
| spellingShingle | Saeed Ranjbar Alvar Mateen Ulhaq Hyomin Choi Ivan V. Bajić Joint image compression and denoising via latent-space scalability Frontiers in Signal Processing image denoising image compression deep learning multi-task compression scalable coding |
| title | Joint image compression and denoising via latent-space scalability |
| title_full | Joint image compression and denoising via latent-space scalability |
| title_fullStr | Joint image compression and denoising via latent-space scalability |
| title_full_unstemmed | Joint image compression and denoising via latent-space scalability |
| title_short | Joint image compression and denoising via latent-space scalability |
| title_sort | joint image compression and denoising via latent space scalability |
| topic | image denoising image compression deep learning multi-task compression scalable coding |
| url | https://www.frontiersin.org/articles/10.3389/frsip.2022.932873/full |
| work_keys_str_mv | AT saeedranjbaralvar jointimagecompressionanddenoisingvialatentspacescalability AT mateenulhaq jointimagecompressionanddenoisingvialatentspacescalability AT hyominchoi jointimagecompressionanddenoisingvialatentspacescalability AT ivanvbajic jointimagecompressionanddenoisingvialatentspacescalability |